AI Threat Alert indexes 3,771+ peer-reviewed and preprint papers on AI/ML security — covering adversarial attacks, model defenses, red-teaming benchmarks, surveys, and security tooling. Papers are sourced from arXiv, classified by type and by relevance to real-world threats, and cross-referenced with the CVEs and incidents they relate to.
Showing 841–860 of 3,771 papers
Haotian Xu, Zeyang Zhang, Linbao Li +3 more
Speculative inference accelerates large language model (LLM) decoding but provides no inherent safety guarantees. Existing safety defenses are...
Gulshan Saleem, Nisar Ahmed, Muhammad Imran Zaman +1 more
Prompt injection is ranked as the most critical vulnerability in large language model (LLM) deployments by the OWASP Top 10 for LLM Applications, yet...
Zunchen Huang, Songgaojun Deng
Formal tools such as SAT and SMT solvers are increasingly embedded in language model reasoning pipelines when a safety or security critical question...
Nils Loose, Jonas Sander, Felix Mächtle +1 more
Large language models (LLMs) are increasingly deployed in sensitive settings such as software engineering, where their outputs directly shape...
R. D. N. Shakya, C. P. Wijesiriwardana, S. M. Vidanagamachchi +1 more
The transition to Post Quantum Cryptography (PQC) introduces considerable implementation complexity, requiring strict adherence to constant-time...
Hannah Le, Ramesh Ramasamy, Alex Urrutia +3 more
Artificial intelligence (AI) agents promise to accelerate drug discovery by compressing interpretation and decision-making loops, but practical...
Hannah Le, Ramesh Ramasamy, Alex Urrutia +3 more
Artificial intelligence (AI) agents promise to accelerate drug discovery by compressing interpretation and decision-making loops, but practical...
Nafiseh Kahani, Masoud Barati, Diana Addae
AI agents now handle personal data through tool use, function calls, and multi turn dialogue, which can create obligations under the General Data...
Po-Han Cheng, Chia-Mu Yu, Ying-Dar Lin +2 more
Code large language models increasingly retrieve external code context from repositories, documentation, issue threads, and coding-agent...
Yu-Ting Lin, Chia-Mu Yu
Agent skills allow LLM-based coding agents to acquire domain-specific capabilities from third-party packages, but they also introduce a new...
Nahum Korda, Gadi Evron
Automated vulnerability discovery in large codebases remains challenging: traditional static analysis produces high false-positive rates, while...
Nahum Korda, Gadi Evron
Automated vulnerability discovery in large codebases remains challenging: traditional static analysis produces high false-positive rates, while...
Ousmane Touat, César Sabater, Mohamed Maouche +1 more
Dealing simultaneously with confidentiality and Byzantine behaviors in decentralized learning is a challenging problem. Indeed, in decentralized...
Ali Safarpoor Dehkordi, Mohammad Shirzadi, Ahad N. Zehmakan
How vulnerable are online social networks to adversaries who seek to amplify opinion polarization by manipulating opinions, and how difficult is it...
Xinjian Luo, Hongyan Chang, Jianxin Wei +5 more
Distributed large language model (LLM) inference frameworks connect isolated consumer-grade devices for large-scale model inference, substantially...
Yibin Hu, Xiaolin Sun, Zizhan Zheng
Model-based learning agents use learned world models to predict future states, plan actions, and adapt to new environments. However, the process of...
Yong Yang, Chong Fu, Tong Zhang +6 more
Large language model (LLM)-based applications rely on system prompts to encode core logic and developer-defined constraints, making these prompts...
Guo-Wei Wong, Ming-Chuan Yang, Shou-De Lin +2 more
In enterprise environments, multiple Advanced Persistent Threat (APT) campaigns often unfold concurrently, producing audit logs in which attack...
Seungwoo Jeong, Moohyun Song, Juhyun Park +1 more
As large language model (LLM) services become widely adopted, the cost of GPU resources for serving these models in cloud environments has emerged as...
Laxmipriya Ganesh Iyer, Rahul Suresh Babu
Risk-Aware Causal Gating (RACG) defends tool-augmented LLM agents against indirect prompt injection by removing dangerous tools from the agent's...
AI security research studies how AI and machine-learning systems can be attacked and defended — covering adversarial examples, prompt injection, model poisoning, training-data extraction, and the mitigations against them. AI Threat Alert curates this research from academic sources so security teams can track the threats behind emerging AI risks.
AI Threat Alert indexes 3,771+ papers on AI/ML security, classified across attack, defense, benchmark, survey, and tool categories and updated continuously.
Papers are sourced from arXiv, then classified by type and by relevance to real-world AI/ML threats, and cross-referenced with the CVEs and incidents they relate to.
Coverage spans adversarial attacks, model and system defenses, red-teaming benchmarks, literature surveys, and security tooling for LLMs, ML libraries, AI agents, and inference pipelines.
Every paper is filtered for AI security relevance and linked to the vulnerabilities, vendors, and incidents it relates to, so the research connects directly to operational threat intelligence.
Get breaking CVE alerts, compliance reports (ISO 42001, EU AI Act), and CISO risk assessments for your AI/ML stack.
Start 14-Day Free Trial
AI Threat Alert